---
library_name: transformers
tags:
- Serbian
- generated_from_trainer
model-index:
- name: childes-segmentation-100k-gpt2_lm-model
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# childes-segmentation-100k-gpt2_lm-model

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- epoch: 4000.0
- eval_absolute_seg_boundary_fscore_Boundary Prediction: 0.5470
- eval_absolute_seg_boundary_fscore_Entropy: 0.4522
- eval_absolute_seg_boundary_fscore_Increase in Boundary Prediction: 0.5803
- eval_absolute_seg_boundary_fscore_Increase in Entropy: 0.4833
- eval_absolute_seg_boundary_fscore_Increase in Loss: 0.5784
- eval_absolute_seg_boundary_fscore_Increase in Rank: 0.6139
- eval_absolute_seg_boundary_fscore_Loss: 0.4960
- eval_absolute_seg_boundary_fscore_Majority Vote Cutoff: 0.6259
- eval_absolute_seg_boundary_fscore_Majority Vote Spike: 0.6291
- eval_absolute_seg_boundary_fscore_Rank: 0.5341
- eval_absolute_seg_type_fscore_Boundary Prediction: 0.3005
- eval_absolute_seg_type_fscore_Entropy: 0.2714
- eval_absolute_seg_type_fscore_Increase in Boundary Prediction: 0.3422
- eval_absolute_seg_type_fscore_Increase in Entropy: 0.2764
- eval_absolute_seg_type_fscore_Increase in Loss: 0.3523
- eval_absolute_seg_type_fscore_Increase in Rank: 0.3931
- eval_absolute_seg_type_fscore_Loss: 0.2706
- eval_absolute_seg_type_fscore_Majority Vote Cutoff: 0.4061
- eval_absolute_seg_type_fscore_Majority Vote Spike: 0.3590
- eval_absolute_seg_type_fscore_Rank: 0.2985
- eval_bpc: 4.5128
- eval_loss: 3.1280
- eval_model_preparation_time: 0.0008
- eval_perplexity: 22.8288
- eval_runtime: 12.2624
- eval_samples_per_second: 12.151
- eval_spike_seg_boundary_fscore_Boundary Prediction: 0.5811
- eval_spike_seg_boundary_fscore_Entropy: 0.4902
- eval_spike_seg_boundary_fscore_Increase in Boundary Prediction: 0.5768
- eval_spike_seg_boundary_fscore_Increase in Entropy: 0.4836
- eval_spike_seg_boundary_fscore_Increase in Loss: 0.5501
- eval_spike_seg_boundary_fscore_Increase in Rank: 0.5845
- eval_spike_seg_boundary_fscore_Loss: 0.5259
- eval_spike_seg_boundary_fscore_Majority Vote Cutoff: 0.6380
- eval_spike_seg_boundary_fscore_Majority Vote Spike: 0.6029
- eval_spike_seg_boundary_fscore_Rank: 0.5890
- eval_spike_seg_type_fscore_Boundary Prediction: 0.2831
- eval_spike_seg_type_fscore_Entropy: 0.2583
- eval_spike_seg_type_fscore_Increase in Boundary Prediction: 0.2799
- eval_spike_seg_type_fscore_Increase in Entropy: 0.2175
- eval_spike_seg_type_fscore_Increase in Loss: 0.2712
- eval_spike_seg_type_fscore_Increase in Rank: 0.3042
- eval_spike_seg_type_fscore_Loss: 0.2594
- eval_spike_seg_type_fscore_Majority Vote Cutoff: 0.3492
- eval_spike_seg_type_fscore_Majority Vote Spike: 0.2747
- eval_spike_seg_type_fscore_Rank: 0.3375
- eval_steps_per_second: 0.408
- step: 100000

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30000
- training_steps: 100000

### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu118
- Datasets 2.18.0
- Tokenizers 0.19.1